Update Changes.

[p5sagit/p5-mst-13.2.git] / ext / Encode / KR / KR.pm

diff --git a/ext/Encode/KR/KR.pm b/ext/Encode/KR/KR.pm
index 9936c5d..55bd9c0 100644 (file)
--- a/ext/Encode/KR/KR.pm
+++ b/ext/Encode/KR/KR.pm
@@ -1,43 +1,69 @@
 package Encode::KR;
-our $VERSION = '0.02';
+BEGIN {
+    if (ord("A") == 193) {
+       die "Encode::KR not supported on EBCDIC\n";
+    }
+}
+our $VERSION = do { my @r = (q$Revision: 1.22 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 
 use Encode;
 use XSLoader;
-XSLoader::load('Encode::KR',$VERSION);
+XSLoader::load(__PACKAGE__,$VERSION);
+
+use Encode::KR::2022_KR;
 
 1;
 __END__
+
 =head1 NAME
 
 Encode::KR - Korean Encodings
 
 =head1 SYNOPSIS
 
-    use Encode::CN;
-    $euc_kr = encode("euc-kr", $utf8);
-    $utf8   = encode("euc-kr", $euc_kr);
+    use Encode qw/encode decode/; 
+    $euc_kr = encode("euc-kr", $utf8);   # loads Encode::KR implicitly
+    $utf8   = decode("euc-kr", $euc_kr); # ditto
 
 =head1 DESCRIPTION
 
 This module implements Korean charset encodings.  Encodings supported
 are as follows.
 
-  euc-kr       EUC (Extended Unix Character)
-  ksc5601      Korean standard code set
-  cp949                Code Page 949 (EUC-KR + Unified Hangul Code)
+
+  Canonical   Alias            Description
+  --------------------------------------------------------------------
+  euc-kr      /\beuc.*kr$/i    EUC (Extended Unix Character)
+             /\bkr.*euc$/i
+  ksc5601-raw                  Korean standard code set (as is)
+  cp949              /(?:x-)?uhc$/i
+              /(?:x-)?windows-949$/i
+              /\bks_c_5601-1987$/i
+                                Code Page 949 (EUC-KR + 8,822 
+                                (additional Hangul syllables)
+  MacKorean                    EUC-KR + Apple Vendor Mappings
+  johab       JOHAB             A supplementary encoding defined in 
+                                             Annex 3 of KS X 1001:1998
+  iso-2022-kr                   iso-2022-kr                  [RFC1557]
+  --------------------------------------------------------------------
   
 To find how to use this module in detail, see L<Encode>.
 
 =head1 BUGS
 
-The C<Johab> (two-byte combination code) encoding is not supported.
+When you see C<charset=ks_c_5601-1987> on mails and web pages, they really
+mean "cp949" encodings.  To fix that, the following aliases are set;
+
+  qr/(?:x-)?uhc$/i         => '"cp949"'
+  qr/(?:x-)?windows-949$/i => '"cp949"'
+  qr/ks_c_5601-1987$/i     => '"cp949"'
 
-ASCII part (0x00-0x7f) is preserved for all encodings, even though it
-conflicts with mappings by the Unicode Consortium.  See
+The ASCII region (0x00-0x7f) is preserved for all encodings, even
+though this conflicts with mappings by the Unicode Consortium.  See
 
-F<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
+L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
 
-to find why it is implemented that way.
+to find out why it is implemented that way.
 
 =head1 SEE ALSO